- If system.instance_id set in config (via env var), use it
- If not set but file exists, read from file (don't generate new)
- If neither, generate new and save to file
Add instance_id field to system section in config.yaml.
Can be set via SYSTEM__INSTANCE_ID env var (auto-mapped).
Falls back to data/labels/instance_id.json if not set.
In SaaS (cloud edition), the instance_id can now be injected via
environment variable to match the pod UUID. This enables zero-lookup
telemetry routing in Space - no need to reverse-lookup instance_id
to find the pod.
Extract knowledge base UUID list into query.variables['_knowledge_base_uuids']
in PreProcessor so plugins can modify it during PromptPreProcessing. Runner now
reads from variables instead of pipeline_config. Also pass session_name,
bot_uuid, and sender_id to kb.retrieve() in the RETRIEVE_KNOWLEDGE_BASE handler
so knowledge engines receive proper session context.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: Implement WebSocket long connection client for WeChat Work AI Bot
- Added WecomBotWsClient to handle WebSocket connections for receiving messages and sending replies.
- Introduced a new migration (dbm022) to add 'enable-webhook' field to existing wecombot adapter configs, ensuring backward compatibility.
- Updated WecomBotAdapter to support both WebSocket and webhook modes based on the new configuration.
- Enhanced YAML configuration for WecomBot to include 'enable-webhook' and 'Secret' fields, adjusting requirements accordingly.
- Incremented database version to 22 to reflect schema changes.
* fix:db enable-webhook is false
* fix:add logic
* fix:Removed an unnecessary configuration check
* fix: migration
* fix: update migration
* fix:migration
* fix(database): Update database version requirement to 20
- Increase required_database_version from 19 to 20
- Add documentation on database schema version check
* feat(lark): Added support for message references and topic message grouping
- Implemented the function to extract reference message IDs from messages, supporting parent message identification
- Added a method to construct event messages from SDK message items
- Implemented the function to asynchronously obtain reference messages and convert them into message chains
- Integrated reference message injection logic into the message processing flow
- Added a mechanism to filter source components while retaining reference content
- Implemented a method to obtain the starter ID with topic awareness
- Provided session isolation support for topic range in group thread messages
- Supported stable maintenance of conversation context in group thread discussions
- Handled cases where topic messages cannot reliably detect reference targets
* feat(lark): Implement a duplicate prevention mechanism for Feishu topic message references
- Add class-level cache to store processed topic IDs and timestamps
- Implement a timed cleanup mechanism to remove expired topic records
- Add cache size limit to prevent memory from growing indefinitely
- Return the parent message ID and mark it as processed when the first reply is made to a topic
- Return None in subsequent replies to the same topic to avoid duplicate references
- Implement automatic cache trimming to ensure stable performance
* fix(market): sync plugin market UI from space - page size 12, full list display, fix double separator, adaptive tag display
* fix: lint and prettier formatting
* fix: prettier formatting for remaining files
- Add get_user_info() to WecomClient to fetch user name via /user/get API
- Update WecomEventConverter.target2yiri to accept bot param and fetch real user name
- Update register_listener call to pass self.bot for user name lookup
- URL-encode userid parameter for safety
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
- Implement full-text search via Chroma's $contains filter
- Implement hybrid search with RRF (Reciprocal Rank Fusion) combining
vector and full-text results, with min-max normalized distances
- Fix add_embeddings to use col.upsert instead of col.add for idempotency
- Bump chromadb dependency to >=1.0.0,<2.0.0
- Re-lock uv.lock with official PyPI source
* feat(rag): add knowledge base migration from v4.9.0 to plugin architecture
Rewrite dbm020 to backup old knowledge_bases data and preserve
external_knowledge_bases table. Add migration API endpoints and
frontend dialog so users can opt-in to auto-install LangRAG plugin
and restore their knowledge bases with original UUIDs preserved.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(rag): query marketplace for actual plugin version instead of 'latest'
The marketplace API does not support 'latest' as a version string.
Fetch the plugin info first to get latest_version, then use that
concrete version for installation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(rag): add data-only migration option and fix dialog width
Add option to migrate knowledge base data without auto-installing
the LangRAG plugin (for offline/intranet environments). Also
narrow the migration dialog to match other confirmation dialogs.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: to red and no more
* fix lint
* fix ruff lint
* feat: add external migration
* fix: show
* feat: add external plugin auto download
* feat: update migration messages for knowledge base in multiple languages
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Junyan Qin <rockchinq@gmail.com>
* fix: coerce pipeline config types at load time using metadata definitions
Pipeline configs stored in SQLAlchemy JSON columns can have values turned
into strings after UI edits (e.g. "120" instead of 120), causing runtime
arithmetic/logic errors. Add centralized type coercion in load_pipeline()
that leverages existing metadata YAML type definitions (integer, number,
float, boolean) to convert values before they reach downstream stages.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address review - defensive getattr + add unit tests for config_coercion
- Use getattr with defaults for pipeline_config_meta_* attributes to
avoid AttributeError when MockApplication lacks these fields
- Add 18 unit tests for config_coercion module covering all code paths
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add dynamic form stage tracking and snapshot management
* fix: standardize string formatting in config coercion and improve logging messages
---------
Co-authored-by: KPC <kpc@kpc.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Junyan Qin <rockchinq@gmail.com>
- Include websocket_proxy_bot in get_bot_by_uuid lookup so plugins can
find it by uuid
- Rewrite send_message to broadcast directly via ws_connection_manager
using the correct pipeline_uuid instead of misusing target_id
- Save messages to session history with unique IDs so they persist
across page reloads and don't overwrite each other
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
- Added dynamic column measurement to adjust the number of visible plugins based on the grid layout.
- Implemented auto-advance feature for pagination every 5 seconds when there are more plugins than the visible count.
- Updated pagination controls to reflect the current page accurately.
- Refactored code to improve readability and maintainability.
The getTitle fallback order was reversed, always showing the UUID
(file_id) since it's always truthy. Swap priority to document_name
first.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
